This LoRA is designed to emphasize the buttocks of female subjects (18+) in lying-down positions, focusing specifically on the exposed glutes from a variety of angles.

The model carries an erotic nature; depending on the camera angle, genitalia may become partially or fully visible. It is specialized for poses where the subject is reclining, with a strict emphasis on prone (face-down) and recumbent orientations.

Subject & Pose Description

The subject is depicted lying down, with the buttocks prominently framed and accentuated. The model supports multiple angles - overhead, rear three-quarter, and side profiles - while consistently maintaining focus on the glutes.

Important: This model is specifically focused on prone position (lying face down) and recumbent side-lying poses. It does not prioritize supine (lying on the back) orientations.

Strength

0.5 - 1.2: Gentle accentuation of the glutes; subtle framing and contouring
1.3 - 2.0: Main features are strongly emphasized; in many cases, the body is fully exposed or nude, with pronounced stylization
2.1 - 2.5: Highly pronounced emphasis on both the body and genitalia
*At these higher strengths, more detailed prompting is required, and balancing with other LoRA models is strongly recommended to maintain composition coherence.
*If the generated image exhibits mutations or anatomical anomalies, it is strongly recommended to adjust the LoRA weight

Image Format Recommendation

The training dataset includes both vertical and horizontal orientations. Therefore, the model performs well with both formats. Choose the aspect ratio that best suits your desired composition.

Training & Captioning Methodology

• Each training image underwent detailed analysis and captioning, taking approximately 4 minutes per image across 8 distinct sections.

• Captions frequently exceed 300 words to capture every nuance of the composition, including object and body descriptions, environment, and camera framing.

Trigger Words & Concepts

While the LoRA responds strongly to natural language prompts describing the pose and focus, it works best with concepts such as:

• lying prone

• side-lying position

• lies in a recumbent pose

• exposed buttocks from behind

• reclining nude

Best Practice

This model was trained exclusively on natural language captions generated by a vision model (Qwen). No Danbooru-style tags were used in the training data.

For best results, use descriptive full sentences in your prompts rather than comma-separated tag lists.

Combining with Other LoRAs

To achieve a wider variety of poses and stylistic variations, it is strongly recommended to mix this LoRA with other LoRA models. This can introduce different body angles, clothing styles, environments, or artistic interpretations while retaining the core focus on the prone and recumbent rear‑glute emphasis.

License & Usage

• You are free to use this model in your projects, including merging or mixing it with other models.

• If you include this LoRA in any merge or mix, please give proper credit.

Support the Creator

If you enjoy my work and want to help cover the electricity costs required to train and refine these models, please consider supporting me:

Address: https://ko-fi.com/weirddreamer (Donations are always appreciated!)